Workflow Automation
Warn
Audited by Snyk on May 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly describes ingesting and acting on external, user-provided content — e.g., public Webhook Triggers ("Public endpoint accessible"), Form Submissions, Event-Driven polling ("fetchChangesSince"), and HTTP Request/CSV parsing — which the agent is expected to read/interpret and which can materially drive workflow actions, creating exposure to untrusted third-party input.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata